© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12178
    Prev
    Next
    INDEX
    Explanations

    template file include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æĻ®æŁ¥
    -0.09
     dul
    -0.09
    趸
    -0.08
    ç¬ijç¬ij
    -0.08
    æ¶Ĥ
    -0.08
    æ³ķå®ļ
    -0.08
    ç½ijä¸Ĭ
    -0.08
     Sle
    -0.08
    çıįæĥľ
    -0.08
    ç°¿
    -0.08
    POSITIVE LOGITS
    æĽ¿ä»£
    0.13
    çĤľ
    0.11
    igy
    0.10
    èĻ±
    0.10
    è¡¿
    0.10
     Twig
    0.09
    æĽ¿æį¢
    0.09
    å®ı
    0.09
    æĬĢå¸Ī
    0.09
    _macros
    0.09
    Activations Density 0.933%

    No Known Activations